FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation

arXiv:2610.18430 · cs.CR, cs.AI · Submitted 2026-10-13 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Accepted at the ICLR 2026 Workshop on Principled Design for Trustworthy AI. This is an author-owned preprint, not the official proceedings version

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Aggregation — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes

Sources

• GPT-4 Technical Report
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
• DeepSeek-V3 Technical Report
• Will we run out of data? Limits of LLM scaling based on human-generated data
• RFLBAT: A Robust Federated Learning Algorithm against Backdoor Attack
• BloombergGPT: A Large Language Model for Finance
• CLLoRA: An Approach to Measure the Effects of the Context Length for LLM Fine-Tuning
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills